Pregled bibliografske jedinice broj: 1072135
Automobile Classification Using Transfer Learning on ResNet Neural Network Architecture
Automobile Classification Using Transfer Learning on ResNet Neural Network Architecture // Polytechnic and design, 8 (2020), 01; 59-64 doi:10.19279/TVZ.PD.2020-8-1-18 (međunarodna recenzija, članak, ostalo)
CROSBI ID: 1072135 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Automobile Classification Using Transfer Learning
on ResNet Neural Network Architecture
Autori
Ložnjak, Stjepan ; Kramberger, Tin ; Cesar, Ivan ; Kramberger, Renata
Izvornik
Polytechnic and design (1849-1995) 8
(2020), 01;
59-64
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, ostalo
Ključne riječi
Transferirano učenje, ResNet, Stanford Car set podataka
(Transfer learning, ResNet, Stanford Car dataset)
Sažetak
Classification is one of the most common problems that neural networks are used for. In the case of higher resolution image classification, convolutional neural networks are commonly used. Due to the reason that convolutional neural networks are so often used in classification, there are many pretrained models that can be adapted for new domains using a technique called transfer learning. This paper shows how excellent results in classification accuracy can be achieved by applying transfer learning to pretrained convolution neural network. This paper presents the results of the learning transfer of the ResNet-152 convolution neural network on the Stanford Cars dataset. The results show accuracy over 88% only by training the last fully connected layer.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Tehničko veleučilište u Zagrebu
